AI for personalized recommendations in the ZDFmediathek

Continuous improvement of the user experience of the ZDFmediathek through AI-supported personalization and automation as part of the public service mandate.
Su So ZDF Header

ZDF is the second public television channel in Germany. With around 15% of the viewer market share, it leads the ranking of television channels (Statista 2024). In order to continue to offer its viewers the best possible user experience, the focus is on further developing the online offering, especially the ZDFmediathek.

Further development of the online offering

ZDF faces several challenges in this further development. One of these is the increasing personalized distribution of content on its own front ends such as TV, apps and third-party platforms such as YouTube. The development of automation systems and AI-supported recommendations, which are increasingly expanding the editorial content selection in the media library, is also becoming more important.
In collaboration with ARD, ZDF is also developing a joint streaming network that enables users to find and play ARD content in the ZDFmediathek. This requires close cooperation and technical integration of both system landscapes.
The basis for all these efforts is the continuous further development of the very complex system landscape and ZDF's own data platform.

Algorithms in the ZDFmediathek: “This might interest you”

The ZDFmediathek offers viewers a personalized and automated service through the use of algorithms, providing them with content tailored to their interests.

The following figure shows the proportion of minutes watched of the use case “Das könnte Dich Interessieren (DKDI)” in the total viewing volume of the ZDFmediathek for automatically recommended content in the last 30 days.

Anteile von gesehenen Minuten des Anwendungsfalls „Das Könnte Dich Interessieren (DKDI)“ am gesamten Sehvolumen der ZDFmediathek für automatisch empfohlene Inhalte der letzten 30 Tage.

We accompany and support the ZDF team from the research of algorithms to the development of recommendation systems and their integration into the existing system landscape through to their operation in the cloud environment. We also support the continuous evolution of the system architecture.

Algorithms are used in various areas:

  • “This might interest you” suggests content that matches their interests in the ZDFmediathek
  • “Also interesting” for recommending similar contributions to the content of the reference contribution
  • “Stage” with recommendations on some stage positions
  • “Because you watched ‘contribution’” suggests thematically similar recommendations to the video you watched
Su So ZDF dkdi
Su So ZDF ai
Su So ZDF bühne
Su So ZDF wdgh

The international project team

2023 HR ZDF Ausflug Community
“A mixed team of ZDF employees and currently 9 Accsonauts from Germany and South Africa are being deployed to solve the diverse tasks in this project. In this way, we combine a wide range of skills that complement each other perfectly and demonstrate our extensive expertise as a digital partner.”Dr. Volker JungPartner Accso
2023 HR ZDF Ausflug Community

Accso covers the following tasks in the overall project:

  • Architecture consulting and further development of the ZDFmediathek and neighboring systems
  • Data engineering, architecture consulting, design, development and operation of the in-house data platform to enable easy exchange of data from multiple sources/departments/systems
  • Data science and R&D (research and development) for recommendation algorithms
  • Software development of the recommendation service and machine learning algorithms
  • DevOps /MLOps and cloud operation in AWS and the Google Cloud
  • Test management and quality assurance

Cooperation based on trust

With our expertise in the field of artificial intelligence, software architecture and development, we support the ZDF team in meeting the constantly evolving requirements of viewers and the market and in continuously improving the ZDFmediathek.

This collaboration has already resulted in several joint publications at German and international conferences such as the ACM Conference on Recommender Systems.

Dr. Volker Jung

Your contact for Media, Portal & Content Solutions
Dr. Volker Jung - Parter bei Accso